位置：成果数据库 > 会议 > 会议详情页
A new language model adaptation framework using modification of structures of background corpus and
  • 所属机构名称：中国科学院自动化研究所
  • 会议名称：2009 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2009
  • 成果类型：会议
  • 会场：Dalian, China
  • 相关项目：基于客观质量评估和音频场景分析语音分离新方法研究
作者： Wenju, Liu|Zhenyu, Lv|Zhanlei, Yang|
同会议论文项目
基于客观质量评估和音频场景分析语音分离新方法研究
期刊论文 36 会议论文 22 获奖 2
同项目会议论文
Masking property based microphone array post-filter design
Learning GMM using elliptically contoured distributions
Speaker adaptation of stochastic segment models using maximum likelihood linear regression
Subspace-based multi-channel speech enhancement using a novel signal subspace dimension estimator in
A novel path extension framework using steady segment detection for mandarin speech recognition
Multi-pitch determination algorithm based on mixture laplacian distribution
Monaural voiced speech segregation based on elaborate harmonic grouping strategy
A Novel Path Extension Framework Using Steady Segment Detection for Mandarin Speech Recognition
Prosody dependent mandarin speech recognition
A novel multi-band spectral subtraction method based on phase modification and magnitude compensatio
Improved Large Vocabulary Mandarin Speech Recognition Using Prosodic and Lexical Information in Maxi
Research on Segment Acoustic Model Based Mandarin LVCSR
HMM-based phonemic distance in different speaking styles and its influence on substitutions in manda
Mandarin pitch accent prediction using hierarchical model based ensemble machine learning
Accelerating Segment Model Decoding for LVCSR by Parallel Processing of Neighboring Segments
Improved Syllable Based Acoustic Modeling by Inter-syllable Transition Model for Continuous Chinese
A novel subspace speech enhancement approach based on test of hypothesis and masking properties
Using prosody to improve Mandarin automatic speech recognition
Mandarin prosodic break detection based on complementary model
Mandarin stress detection using hierarchical model based boosting classification and regression tree
An Improvement of HSMM-Based Speech Synthesis by Duration-Dependent State Transition Probabilities